SELECT 中多个聚合的优化

Question

我在Microsoft T-SQL Performance Tuning whitepaper 中读到，相关子查询在大型表上的性能方面可能代价高昂：

...将此与第一个进行比较 扫描整个表并为每个表执行相关子查询的解决方案 排。在一张小桌子上，性能上的差异可以忽略不计。但在一张大桌子上 可能需要数小时的处理时间...

是否有一种通用方法可以将具有基于不同标准的多个聚合的查询作为相关子查询转换为使用JOINs 而不是相关子查询的单个查询？

考虑一个例子：

准备架构：

CREATE TABLE Student (
    ID INT NOT NULL PRIMARY KEY IDENTITY(1,1),
    Name NVARCHAR(255) NOT NULL
);

CREATE TABLE Grade (
    ID INT NOT NULL PRIMARY KEY IDENTITY(1,1),
    StudentID INT NOT NULL FOREIGN KEY REFERENCES Student(ID),
    Score INT NOT NULL,
    CONSTRAINT CK_Grade_Score CHECK (Score >= 0 AND Score <= 100)
);

INSERT INTO Student (Name) VALUES ('Steven');
INSERT INTO Student (Name) VALUES ('Timmy');
INSERT INTO Student (Name) VALUES ('Maria');
 
INSERT INTO Grade (StudentID, Score) VALUES (1, 90);
INSERT INTO Grade (StudentID, Score) VALUES (1, 81);
INSERT INTO Grade (StudentID, Score) VALUES (1, 82);
INSERT INTO Grade (StudentID, Score) VALUES (1, 82);

INSERT INTO Grade (StudentID, Score) VALUES (2, 99);
INSERT INTO Grade (StudentID, Score) VALUES (2, 63);
INSERT INTO Grade (StudentID, Score) VALUES (2, 97);
INSERT INTO Grade (StudentID, Score) VALUES (2, 90);

INSERT INTO Grade (StudentID, Score) VALUES (3, 66);
INSERT INTO Grade (StudentID, Score) VALUES (3, 61);
INSERT INTO Grade (StudentID, Score) VALUES (3, 60);

有问题的查询：

SELECT Name,
    (SELECT AVG(Score) FROM Grade WHERE StudentID = Student.ID AND Score < 65) AS 'F',
    (SELECT AVG(Score) FROM Grade WHERE StudentID = Student.ID AND Score >= 65 AND Score < 70) AS 'D',
    (SELECT AVG(Score) FROM Grade WHERE StudentID = Student.ID AND Score >= 70 AND Score < 80) AS 'C',
    (SELECT AVG(Score) FROM Grade WHERE StudentID = Student.ID AND Score >= 80 AND Score < 90) AS 'B',
    (SELECT AVG(Score) FROM Grade WHERE StudentID = Student.ID AND Score >= 90 AND Score <= 100) AS 'A'
FROM Student

产生以下结果：

Name    F     D     C     B     A
-----------------------------------------
Steven  NULL  NULL  NULL  81    90
Timmy   63    NULL  NULL  NULL  95
Maria   60    66    NULL  NULL  NULL

我知道您可以在 COUNT() 中使用的技术，您可以在其中执行单个 SELECT 和 JOIN，然后使用 CASE 语句在主键行时选择性地向计数器添加 1在您的加入和您的条件为真之间。我正在寻找一种类似的技术，可以应用于不同类型的聚合（而不仅仅是COUNT）。

有没有一种有效的方法可以将此示例查询转换为使用JOIN 而不是多个子查询？

Answer 1

也许我遗漏了一些东西，但使用 CASE 的解决方案也适用于聚合：

SELECT st.name, 
       avg(CASE WHEN g.score < 65 THEN g.score ELSE NULL END) as F,
       avg(CASE WHEN g.score >= 65 AND g.score < 70 THEN g.score ELSE NULL END) as D,
       avg(CASE WHEN g.score >= 70 AND g.score < 80 THEN g.score ELSE NULL END) as C,
       avg(CASE WHEN g.score >= 80 AND g.score < 90 THEN g.score ELSE NULL END) as B,
       avg(CASE WHEN g.score >= 90 AND g.score <= 100 THEN g.score ELSE NULL END) as A
FROM Grade g
  JOIN Student st ON g.studentid = st.ID
GROUP BY st.name

Answer 2

我使用 CTE 尝试了类似以下的操作，但结果与您得到的有点不同，因为它计算的是所有成绩的平均值：

;WITH
Scores(ID,Score) AS(
    SELECT S.ID,AVG(Score)
    FROM Student S
    JOIN Grade G
        ON S.ID = G.StudentID
    GROUP BY S.ID)

SELECT ST.Name
    ,CASE WHEN S.Score  < 65 THEN S.Score ELSE NULL END AS 'F'
    ,CASE WHEN S.Score  BETWEEN 65 AND 70 THEN S.Score ELSE NULL END AS 'D'
    ,CASE WHEN S.Score  BETWEEN 70 AND 80 THEN S.Score ELSE NULL END AS 'C'
    ,CASE WHEN S.Score  BETWEEN 80 AND 90 THEN S.Score ELSE NULL END AS 'B'
    ,CASE WHEN S.Score  BETWEEN 90 AND 100 THEN S.Score ELSE NULL END AS 'A'
FROM Scores S
JOIN Student ST
    ON S.ID = ST.ID

Answer 3

试试这个：

SELECT s.Name
    ,SUM(CASE Score_g WHEN 'F' THEN Score_avg END) as 'F'
    ,SUM(CASE Score_g WHEN 'D' THEN Score_avg END) as 'D'
    ,SUM(CASE Score_g WHEN 'C' THEN Score_avg END) as 'C'
    ,SUM(CASE Score_g WHEN 'B' THEN Score_avg END) as 'B'
    ,SUM(CASE Score_g WHEN 'A' THEN Score_avg END) as 'A'
FROM Student s,
     (
      SELECT StudentId, score_g, avg(score) as score_avg
      FROM  (
            SELECT StudentID, Score
            CASE
              WHEN Score < 65                   THEN 'F'
              WHEN Score >= 65 AND Score < 70   THEN 'D'
              WHEN Score >= 70 AND Score < 80   THEN 'C'
              WHEN Score >= 80 AND Score < 90     THEN 'B'
              WHEN Score >= 90 AND Score <= 100 THEN 'A'
              ELSE 'X'
            END AS Score_g
            FROM Grade
        ) g
       GROUP BY StudentId, score_g
    ) t
WHERE s.ID = t.StudentID
GROUP BY s.Name

如果你真的讨厌子查询，你可以使用：

SELECT s.name
    ,AVG(CASE WHEN Score < 65                   THEN SCORE END) AS 'F'
    ,AVG(CASE WHEN Score >= 65 AND Score < 70   THEN SCORE  END) AS 'D'
    ,AVG(CASE WHEN Score >= 70 AND Score < 80   THEN SCORE  END) AS 'C'
    ,AVG(CASE WHEN Score >= 80 AND Score < 90     THEN SCORE END) AS 'B'
    ,AVG(CASE WHEN Score >= 90 AND Score <= 100 THEN SCORE  END) AS 'A'
FROM Grade g, Student s
WHERE g.StudentID = s.ID
GROUP BY s.name

但在这种情况下，学生表必须包含一个学生实体的唯一条目。

Answer 4

如果你的 DBMS 支持PIVOT，你也可以试试这样的：

;WITH marked AS (
  SELECT
    StudentID,
    Score,
    Mark = CASE
      WHEN Score < 65 THEN 'F'
      WHEN Score < 70 THEN 'D'
      WHEN Score < 80 THEN 'C'
      WHEN Score < 90 THEN 'B'
      ELSE 'A'
    END
  FROM Grade
),
pivoted AS (
  SELECT
    StudentID,
    F, D, C, B, A
  FROM marked m
  PIVOT (
    AVG(Score) FOR Mark IN (F, D, C, B, A)
  ) p
)
SELECT
  s.Name,
  p.F,
  p.D,
  p.C,
  p.B,
  p.A
FROM Student s
  INNER JOIN pivoted p ON s.ID = p.StudentID